Instructions to use llmware/slim-sa-ner-tool with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/slim-sa-ner-tool with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("llmware/slim-sa-ner-tool", dtype="auto")

llama-cpp-python

How to use llmware/slim-sa-ner-tool with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="llmware/slim-sa-ner-tool",
	filename="sa-ner.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use llmware/slim-sa-ner-tool with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/slim-sa-ner-tool
# Run inference directly in the terminal:
llama-cli -hf llmware/slim-sa-ner-tool

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/slim-sa-ner-tool
# Run inference directly in the terminal:
llama-cli -hf llmware/slim-sa-ner-tool

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf llmware/slim-sa-ner-tool
# Run inference directly in the terminal:
./llama-cli -hf llmware/slim-sa-ner-tool

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf llmware/slim-sa-ner-tool
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmware/slim-sa-ner-tool

Use Docker

docker model run hf.co/llmware/slim-sa-ner-tool

LM Studio
Jan
Ollama
How to use llmware/slim-sa-ner-tool with Ollama:
```
ollama run hf.co/llmware/slim-sa-ner-tool
```

Unsloth Studio

How to use llmware/slim-sa-ner-tool with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for llmware/slim-sa-ner-tool to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for llmware/slim-sa-ner-tool to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for llmware/slim-sa-ner-tool to start chatting

Docker Model Runner
How to use llmware/slim-sa-ner-tool with Docker Model Runner:
```
docker model run hf.co/llmware/slim-sa-ner-tool
```

Lemonade

How to use llmware/slim-sa-ner-tool with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmware/slim-sa-ner-tool

Run and chat with the model

lemonade run user.slim-sa-ner-tool-{{QUANT_TAG}}

List all available models

lemonade list

doberst113080 commited on Mar 20, 2024

Commit

2afbcf0

verified ·

1 Parent(s): 8025da6

Update config.json

Browse files

Files changed (1) hide show

config.json +8 -20

config.json CHANGED Viewed

@@ -1,29 +1,17 @@
 {
- "model_name": "slim-sa-ner-tool",
- "model_ft_base": "slim-sa-ner",
  "quantization": "4Q_K_M GGUF",
  "model_base": "stabilityai/stablelm-3b-4e1t",
  "model_type": "stablelm",
- "tokenizer": "llmware/slim-sa-ner",
  "parameters": "2.7 billion",
- "description": "slim-sa-ner is a function-calling model, fine-tuned to output structured dictionaries corresponding to sentiment analysis classification and major named entity categories",
  "prompt_wrapper": "human_bot",
- "prompt_format": "<human> {context_passage} <classify> sentiment, people, place, organization, misc </classify>\n<bot>:",
- "output_format": "{'sentiment': [], 'people': [], 'place': [], 'organization': [], 'misc':[]}",
- "primary_keys": [
-  "sentiment",
-  "people",
-  "place",
-  "organization",
-  "misc"
- ],
- "output_values": [
-  "sentiment",
-  "people",
-  "place",
-  "organization",
-  "misc"
- ],
  "publisher": "llmware",
  "release_date": "march 2024",
  "test_set": [

 {
+ "model_name": "slim-extract-tool",
+ "model_ft_base": "slim-extract",
  "quantization": "4Q_K_M GGUF",
  "model_base": "stabilityai/stablelm-3b-4e1t",
  "model_type": "stablelm",
+ "tokenizer": "llmware/slim-extract",
  "parameters": "2.7 billion",
+ "description": "slim-extract is a function-calling model, fine-tuned to output structured dictionaries corresponding to a custom extraction key",
  "prompt_wrapper": "human_bot",
+ "prompt_format": "<human> {context_passage} <classify> {custom extraction key} </classify>\n<bot>:",
+ "output_format": "{custom_extraction_key: ['list of items found in the text corresponding to key']}",
+ "primary_keys": ["any custom key provided"],
+ "output_values": ["dictionary with custom_key and value consisting of list of extracted values"],
  "publisher": "llmware",
  "release_date": "march 2024",
  "test_set": [